Skill Validation

springboot-verification is a verification loop for Spring Boot projects that helps you confirm a change is safe before a PR or deploy. Use this springboot-verification guide for build validation, static analysis, tests with coverage, security scans, and Skill Validation.

santa-method is a multi-agent verification workflow for outputs that need to be right before they ship. It uses independent review to catch blind spots in content, code-adjacent deliverables, compliance-sensitive copy, and workflow automation tasks. Install the santa-method skill when you need a repeatable generate, verify, converge loop.

rules-distill is a maintenance skill for Skill Authors and prompt library curators. It scans installed skills, distills repeated patterns into reusable rules, and helps you append, revise, or create rule files with less guesswork than a generic review prompt.

The eval-harness skill is a formal evaluation framework for Claude Code sessions and eval-driven development. It helps you define pass/fail criteria, build capability and regression evals, and measure agent reliability before shipping prompt or workflow changes.

continuous-learning-v2 turns Claude Code sessions into project-scoped learning with hooks, observer agents, confidence scoring, and promotion of repeated patterns into skills, commands, or agents.

The context-budget skill audits Claude Code context use across agents, skills, rules, and MCP servers. It helps identify bloat, duplicate content, and high-cost components, then returns prioritized cleanup actions. Use this context-budget guide for practical context-budget usage and for Skill Testing in larger setups.

agent-sort is a repo-aware skill for building an evidence-backed ECC install plan. It helps sort skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets so you install only what the project actually uses. Use the agent-sort skill for install decisions, agent-sort usage, and a practical agent-sort guide for Skill Authoring workflows.

writing-skills is a Skill Authoring guide for creating, editing, and validating agent skills with a test-driven workflow. Learn the key files, prerequisites, and practical steps for pressure scenarios, baseline tests, and concise SKILL.md iteration.

verification-before-completion is a final-check skill that blocks unsupported completion claims. Learn when to use it, how to install it from obra/superpowers, and how to match each status claim to fresh verification evidence.

skill-creator is a Skill Authoring meta-skill for drafting new skills, revising existing SKILL.md files, running evals, comparing variants, and improving trigger descriptions with repository scripts and review tools.

The evaluation-methodology skill explains PluginEval scoring for Model Evaluation, including layers, rubrics, composite scoring, badge thresholds, and practical guidance for interpreting results and improving weak dimensions.

context-degradation is a practical skill for diagnosing context failures in long workflows, including lost-in-the-middle, poisoning, distraction, confusion, and clash. Use it to identify where context breaks, decide what to change first, and apply a repeatable context-degradation guide for Skill Authoring, prompt placement, and production agent debugging.

context-fundamentals is a practical guide to context engineering for AI agent systems. It helps you decide what belongs in the prompt, debug context issues, and manage token budgets with clearer context structure. Use this context-fundamentals skill when you need a grounded context-fundamentals guide for agent design and prompt optimization.

skill-builder helps skill authors turn docs, GitHub repos, PDFs, videos, and codebases into AI-ready skills with Skill Seekers. It includes source-type detection, a recommended workflow, and tool-based steps for repeatable skill authoring instead of one-off prompting.

testing-handbook-generator is a meta-skill for creating Claude Code skills from the Trail of Bits Testing Handbook (appsec.guide). It helps skill authors, security engineers, and maintainers turn handbook sections into reusable skills with a clear workflow, scope control, and repeatable generation. Use the testing-handbook-generator skill when you need a testing-handbook-generator guide for handbook-to-skill authoring.

audit-prep-assistant prepares codebases for Security Audit using Trail of Bits' checklist. It helps set review goals, run static analysis, increase test coverage, remove dead code, document risks, and generate supporting artifacts for a cleaner audit handoff.

create-skill-test scaffolds eval.yaml test files for agent skills in dotnet/skills. Use it to create skill tests, define scenarios, fixtures, assertions, and rubrics, and reduce overfitting in evaluation design. It is not for running existing tests, debugging validator errors, or authoring SKILL.md files.

create-skill is a scaffold generator for new agent skills in the dotnet/skills style. Use it to create a valid skill folder, generate SKILL.md with frontmatter, and follow repository conventions for Skill Scaffolding. It is best for new skills, not editing existing ones.

skill-optimizer helps authors improve AI skills for activation, clarity, and cross-model reliability. Use it for Skill Authoring when a skill is written but not reliably followed, when triggers are weak, regressions appear, or context cost needs trimming. It supports benchmark loops, release gates, and tighter usage fidelity.

skill-judge is a review and scoring skill for auditing AI skill packages and SKILL.md files. It helps authors and maintainers judge knowledge delta, activation clarity, workflow quality, and publish readiness with actionable improvement guidance.

Judge is a two-phase evaluation skill that launches a meta-judge first, then a judge sub-agent to score work with isolated context, evidence, and clear criteria. Use it for report-only reviews of code, writing, analysis, or Skill Authoring when you need a defensible judge guide instead of a casual opinion.

The do-and-judge skill executes a single task with a sub-agent implementation step, an independent judge, and retry-based verification until it passes or max retries are reached. Use do-and-judge for Workflow Automation when you need clear acceptance criteria, isolated execution, and less guesswork than a generic prompt.

llm-patterns helps you design AI-first application logic where LLMs handle reasoning, extraction, and generation while code handles validation, routing, and error handling. Use the llm-patterns skill for clearer prompt structure, testable LLM workflows, and practical guidance for Skill Authoring.

darwin-skill helps improve SKILL.md files with a repeatable loop: evaluate, revise, test, then keep or revert changes. Built for Skill Authoring, it combines rubric scoring with prompt-based validation and supports visual result outputs from repo templates and assets.